An accurate method for image quality evaluation using digital watermarking

Abstract

This paper presents a watermarking-based image quality evaluation method that estimates image quality in terms of classical objective metrics, such as PSNR, wPSNR, and Watson JND, without the need for original image. Considering the different frequency distribution of image, the watermark is embedded into the original image and its vulnerability is adjusted using automatic control. After processing, the degradation of the extracted watermark is used to estimate image quality in terms of the classical metrics. By comparing the image quality obtained by the proposed method with the calculated PSNR, wPSNR, and JND, it is clear that the proposed method can be used to evaluate image quality against JPEG compression with high accuracy.